© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 954
    Prev
    Next
    INDEX
    Explanations

    technical/scientific contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.97
    EndGlobalSection
    -0.91
    contentLoaded
    -0.84
    TagMode
    -0.82
    Personendaten
    -0.81
    webElementXpaths
    -0.79
    RTEE
    -0.78
     actionMode
    -0.77
     صوتيه
    -0.77
     ſeveral
    -0.75
    POSITIVE LOGITS
     it
    0.56
    其中
    0.48
    ,
    0.47
     which
    0.46
    oland
    0.41
     there
    0.40
     mit
    0.40
    vail
    0.39
    inetto
    0.39
    RTCF
    0.38
    Activations Density 0.000%

    No Known Activations